Headed-Span-Based Projective Dependency Parsing

Code

• github.com/sustcsonglin/span-based-dependency-parsing
  OfficialIn paperpytorch★ 16

Abstract

We propose a new method for projective dependency parsing based on headed spans. In a projective dependency tree, the largest subtree rooted at each word covers a contiguous sequence (i.e., a span) in the surface order. We call such a span marked by a root word headed span. A projective dependency tree can be represented as a collection of headed spans. We decompose the score of a dependency tree into the scores of the headed spans and design a novel O(n^3) dynamic programming algorithm to enable global training and exact inference. Our model achieves state-of-the-art or competitive results on PTB, CTB, and UD. Our code is publicly available at https://github.com/sustcsonglin/span-based-dependency-parsing.

Tasks

Reproductions